Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2018

AUTHORS

Dwarikanath Mahapatra , Behzad Bozorgtabar , Jean-Philippe Thiran , Mauricio Reyes

ABSTRACT

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples and add to the training data. We use conditional generative adversarial networks (cGANs) to generate realistic chest xray images with different disease characteristics by conditioning its generation on a real image sample. Informative samples to add to the training set are identified using a Bayesian neural network. Experiments show our proposed AL framework is able to achieve state of the art performance by using about \(35\%\) of the full dataset, thus saving significant time and effort over conventional methods. More... »

PAGES

580-588

References to SciGraph publications

  • 2013. Semi-Supervised and Active Learning for Automatic Segmentation of Crohn’s Disease in ADVANCED INFORMATION SYSTEMS ENGINEERING
  • 2017. Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION − MICCAI 2017
  • 2017. Image Super Resolution Using Generative Adversarial Networks and Local Saliency Maps for Retinal Image Analysis in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION − MICCAI 2017
  • 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION – MICCAI 2015
  • Book

    TITLE

    Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

    ISBN

    978-3-030-00933-5
    978-3-030-00934-2

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-030-00934-2_65

    DOI

    http://dx.doi.org/10.1007/978-3-030-00934-2_65

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1107024340


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "IBM Research - Australia", 
              "id": "https://www.grid.ac/institutes/grid.481553.e", 
              "name": [
                "IBM Research Australia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mahapatra", 
            "givenName": "Dwarikanath", 
            "id": "sg:person.01100662063.91", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01100662063.91"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne", 
              "id": "https://www.grid.ac/institutes/grid.5333.6", 
              "name": [
                "Ecole Polytechnique Federale de Lausanne"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bozorgtabar", 
            "givenName": "Behzad", 
            "id": "sg:person.013213672445.40", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013213672445.40"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne", 
              "id": "https://www.grid.ac/institutes/grid.5333.6", 
              "name": [
                "Ecole Polytechnique Federale de Lausanne"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Thiran", 
            "givenName": "Jean-Philippe", 
            "id": "sg:person.01056563742.51", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01056563742.51"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Bern", 
              "id": "https://www.grid.ac/institutes/grid.5734.5", 
              "name": [
                "University of Bern"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Reyes", 
            "givenName": "Mauricio", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.media.2005.02.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002136321"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.media.2005.02.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002136321"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-24574-4_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017774818", 
              "https://doi.org/10.1007/978-3-319-24574-4_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-40763-5_27", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027682231", 
              "https://doi.org/10.1007/978-3-642-40763-5_27"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tcsvt.2016.2589879", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061576837"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tmi.2016.2535302", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061696712"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-66179-7_46", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091428982", 
              "https://doi.org/10.1007/978-3-319-66179-7_46"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-66179-7_44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091432173", 
              "https://doi.org/10.1007/978-3-319-66179-7_44"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.90", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093359587"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.116", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093551533"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.116", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093551533"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.278", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095706293"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.369", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095848734"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.632", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095850445"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018", 
        "datePublishedReg": "2018-01-01", 
        "description": "Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples and add to the training data. We use conditional generative adversarial networks (cGANs) to generate realistic chest xray images with different disease characteristics by conditioning its generation on a real image sample. Informative samples to add to the training set are identified using a Bayesian neural network. Experiments show our proposed AL framework is able to achieve state of the art performance by using about \\(35\\%\\) of the full dataset, thus saving significant time and effort over conventional methods.", 
        "editor": [
          {
            "familyName": "Frangi", 
            "givenName": "Alejandro F.", 
            "type": "Person"
          }, 
          {
            "familyName": "Schnabel", 
            "givenName": "Julia A.", 
            "type": "Person"
          }, 
          {
            "familyName": "Davatzikos", 
            "givenName": "Christos", 
            "type": "Person"
          }, 
          {
            "familyName": "Alberola-L\u00f3pez", 
            "givenName": "Carlos", 
            "type": "Person"
          }, 
          {
            "familyName": "Fichtinger", 
            "givenName": "Gabor", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-030-00934-2_65", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-030-00933-5", 
            "978-3-030-00934-2"
          ], 
          "name": "Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018", 
          "type": "Book"
        }, 
        "name": "Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network", 
        "pagination": "580-588", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-030-00934-2_65"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "7190f676f90930ed5925e86fd94f8f1bbfc1d9d3127a235f6b6825f03177446c"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1107024340"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-030-00934-2_65", 
          "https://app.dimensions.ai/details/publication/pub.1107024340"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T19:49", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8684_00000605.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-030-00934-2_65"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00934-2_65'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00934-2_65'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00934-2_65'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00934-2_65'


     

    This table displays all metadata directly associated to this object as RDF triples.

    151 TRIPLES      23 PREDICATES      39 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-030-00934-2_65 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N2e9d55727cf14045ab919a3b83aae55d
    4 schema:citation sg:pub.10.1007/978-3-319-24574-4_28
    5 sg:pub.10.1007/978-3-319-66179-7_44
    6 sg:pub.10.1007/978-3-319-66179-7_46
    7 sg:pub.10.1007/978-3-642-40763-5_27
    8 https://doi.org/10.1016/j.media.2005.02.002
    9 https://doi.org/10.1109/cvpr.2013.116
    10 https://doi.org/10.1109/cvpr.2016.278
    11 https://doi.org/10.1109/cvpr.2016.90
    12 https://doi.org/10.1109/cvpr.2017.369
    13 https://doi.org/10.1109/cvpr.2017.632
    14 https://doi.org/10.1109/tcsvt.2016.2589879
    15 https://doi.org/10.1109/tmi.2016.2535302
    16 schema:datePublished 2018
    17 schema:datePublishedReg 2018-01-01
    18 schema:description Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples and add to the training data. We use conditional generative adversarial networks (cGANs) to generate realistic chest xray images with different disease characteristics by conditioning its generation on a real image sample. Informative samples to add to the training set are identified using a Bayesian neural network. Experiments show our proposed AL framework is able to achieve state of the art performance by using about \(35\%\) of the full dataset, thus saving significant time and effort over conventional methods.
    19 schema:editor Nfebac6656b75489685eda1039cc44d03
    20 schema:genre chapter
    21 schema:inLanguage en
    22 schema:isAccessibleForFree true
    23 schema:isPartOf Nc5c8c1c634504cb586e7019b1c2596bf
    24 schema:name Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network
    25 schema:pagination 580-588
    26 schema:productId N5a0af6c2c97141ff990de69e75001942
    27 N8c34723f6ffe46389ade09daaad52d71
    28 Ndbd13cd7419e4c218525428c22420ae7
    29 schema:publisher Nbd1670d20ddf4051a2f2c30c94c2dc12
    30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107024340
    31 https://doi.org/10.1007/978-3-030-00934-2_65
    32 schema:sdDatePublished 2019-04-15T19:49
    33 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    34 schema:sdPublisher N78306642e1c74535b40be8cdbed481f3
    35 schema:url http://link.springer.com/10.1007/978-3-030-00934-2_65
    36 sgo:license sg:explorer/license/
    37 sgo:sdDataset chapters
    38 rdf:type schema:Chapter
    39 N2e9d55727cf14045ab919a3b83aae55d rdf:first sg:person.01100662063.91
    40 rdf:rest N7bdc1f7e933f44b3bb39fd919a352a79
    41 N312761713676494dab0fbe9654710509 rdf:first N5071b216397f4e3dab91b572057439ef
    42 rdf:rest Ne7594004a51b47749c69d06eb411a065
    43 N31e133dfcc414f4daebac6c962265926 schema:familyName Frangi
    44 schema:givenName Alejandro F.
    45 rdf:type schema:Person
    46 N4dfb02ce50e54f04a7973cdbbf86bd4f schema:familyName Davatzikos
    47 schema:givenName Christos
    48 rdf:type schema:Person
    49 N5071b216397f4e3dab91b572057439ef schema:familyName Alberola-López
    50 schema:givenName Carlos
    51 rdf:type schema:Person
    52 N50e968ac75254a909f31ad31782bc253 schema:affiliation https://www.grid.ac/institutes/grid.5734.5
    53 schema:familyName Reyes
    54 schema:givenName Mauricio
    55 rdf:type schema:Person
    56 N56e61382c2114c2eac770ac5cdb27931 schema:familyName Fichtinger
    57 schema:givenName Gabor
    58 rdf:type schema:Person
    59 N5a0af6c2c97141ff990de69e75001942 schema:name doi
    60 schema:value 10.1007/978-3-030-00934-2_65
    61 rdf:type schema:PropertyValue
    62 N5a99ea52e0da48b6a927b9b262663fe6 rdf:first sg:person.01056563742.51
    63 rdf:rest N6430cf44176b466991c478a4d5512713
    64 N6430cf44176b466991c478a4d5512713 rdf:first N50e968ac75254a909f31ad31782bc253
    65 rdf:rest rdf:nil
    66 N67e741f0e1b94aac8f31a2abdf19956b rdf:first N4dfb02ce50e54f04a7973cdbbf86bd4f
    67 rdf:rest N312761713676494dab0fbe9654710509
    68 N78306642e1c74535b40be8cdbed481f3 schema:name Springer Nature - SN SciGraph project
    69 rdf:type schema:Organization
    70 N7bdc1f7e933f44b3bb39fd919a352a79 rdf:first sg:person.013213672445.40
    71 rdf:rest N5a99ea52e0da48b6a927b9b262663fe6
    72 N7f1f9a4379ff453d94b152489a35cdab schema:familyName Schnabel
    73 schema:givenName Julia A.
    74 rdf:type schema:Person
    75 N8c34723f6ffe46389ade09daaad52d71 schema:name readcube_id
    76 schema:value 7190f676f90930ed5925e86fd94f8f1bbfc1d9d3127a235f6b6825f03177446c
    77 rdf:type schema:PropertyValue
    78 Nbd1670d20ddf4051a2f2c30c94c2dc12 schema:location Cham
    79 schema:name Springer International Publishing
    80 rdf:type schema:Organisation
    81 Nc5c8c1c634504cb586e7019b1c2596bf schema:isbn 978-3-030-00933-5
    82 978-3-030-00934-2
    83 schema:name Medical Image Computing and Computer Assisted Intervention – MICCAI 2018
    84 rdf:type schema:Book
    85 Ndbd13cd7419e4c218525428c22420ae7 schema:name dimensions_id
    86 schema:value pub.1107024340
    87 rdf:type schema:PropertyValue
    88 Ne7594004a51b47749c69d06eb411a065 rdf:first N56e61382c2114c2eac770ac5cdb27931
    89 rdf:rest rdf:nil
    90 Ne94068d6bcb24936921ba32dcbdb5e0b rdf:first N7f1f9a4379ff453d94b152489a35cdab
    91 rdf:rest N67e741f0e1b94aac8f31a2abdf19956b
    92 Nfebac6656b75489685eda1039cc44d03 rdf:first N31e133dfcc414f4daebac6c962265926
    93 rdf:rest Ne94068d6bcb24936921ba32dcbdb5e0b
    94 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Information and Computing Sciences
    96 rdf:type schema:DefinedTerm
    97 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    98 schema:name Artificial Intelligence and Image Processing
    99 rdf:type schema:DefinedTerm
    100 sg:person.01056563742.51 schema:affiliation https://www.grid.ac/institutes/grid.5333.6
    101 schema:familyName Thiran
    102 schema:givenName Jean-Philippe
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01056563742.51
    104 rdf:type schema:Person
    105 sg:person.01100662063.91 schema:affiliation https://www.grid.ac/institutes/grid.481553.e
    106 schema:familyName Mahapatra
    107 schema:givenName Dwarikanath
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01100662063.91
    109 rdf:type schema:Person
    110 sg:person.013213672445.40 schema:affiliation https://www.grid.ac/institutes/grid.5333.6
    111 schema:familyName Bozorgtabar
    112 schema:givenName Behzad
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013213672445.40
    114 rdf:type schema:Person
    115 sg:pub.10.1007/978-3-319-24574-4_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017774818
    116 https://doi.org/10.1007/978-3-319-24574-4_28
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/978-3-319-66179-7_44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091432173
    119 https://doi.org/10.1007/978-3-319-66179-7_44
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1007/978-3-319-66179-7_46 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091428982
    122 https://doi.org/10.1007/978-3-319-66179-7_46
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1007/978-3-642-40763-5_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027682231
    125 https://doi.org/10.1007/978-3-642-40763-5_27
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1016/j.media.2005.02.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002136321
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/cvpr.2013.116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093551533
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/cvpr.2016.278 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095706293
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/cvpr.2016.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359587
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/cvpr.2017.369 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095848734
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1109/cvpr.2017.632 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095850445
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1109/tcsvt.2016.2589879 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061576837
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1109/tmi.2016.2535302 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061696712
    142 rdf:type schema:CreativeWork
    143 https://www.grid.ac/institutes/grid.481553.e schema:alternateName IBM Research - Australia
    144 schema:name IBM Research Australia
    145 rdf:type schema:Organization
    146 https://www.grid.ac/institutes/grid.5333.6 schema:alternateName École Polytechnique Fédérale de Lausanne
    147 schema:name Ecole Polytechnique Federale de Lausanne
    148 rdf:type schema:Organization
    149 https://www.grid.ac/institutes/grid.5734.5 schema:alternateName University of Bern
    150 schema:name University of Bern
    151 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...